Prediction of Overall Survival in Cervical Cancer Patients Using PET/CT Radiomic Features

被引:6
作者
Carlini, Gianluca [1 ]
Curti, Nico [2 ]
Strolin, Silvia [3 ]
Giampieri, Enrico [2 ]
Sala, Claudia [2 ]
Dall'Olio, Daniele [1 ]
Merlotti, Alessandra [1 ]
Fanti, Stefano [4 ,5 ]
Remondini, Daniel [1 ,6 ]
Nanni, Cristina [5 ]
Strigari, Lidia [3 ]
Castellani, Gastone [2 ]
机构
[1] Univ Bologna, Dept Phys & Astron, I-40126 Bologna, Italy
[2] Univ Bologna, Dept Expt Diagnost & Specialty Med, I-40126 Bologna, Italy
[3] IRCCS Azienda Osped Univ Bologna, Dept Med Phys, I-40126 Bologna, Italy
[4] Univ Bologna, Dept Expt Diagnost & Specialty Med, Nucl Med, I-40126 Bologna, Italy
[5] Azienda Osped Univ Bologna, IRCCS, Nucl Med, I-40138 Bologna, Italy
[6] INFN Bologna, I-40127 Bologna, Italy
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 12期
关键词
cervical cancer; survival analysis; radiomics; PET; CT; HETEROGENEITY;
D O I
10.3390/app12125946
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Background: Radiomics is a field of research medicine and data science in which quantitative imaging features are extracted from medical images and successively analyzed to develop models for providing diagnostic, prognostic, and predictive information. The purpose of this work was to develop a machine learning model to predict the survival probability of 85 cervical cancer patients using PET and CT radiomic features as predictors. Methods: Initially, the patients were divided into two mutually exclusive sets: a training set containing 80% of the data and a testing set containing the remaining 20%. The entire analysis was separately conducted for CT and PET features. Genetic algorithms and LASSO regression were used to perform feature selection on the initial PET and CT feature sets. Two different survival models were employed: the Cox proportional hazard model and random survival forest. The Cox model was built using the subset of features obtained with the feature selection process, while all the available features were used for the random survival forest model. The models were trained on the training set; cross-validation was used to fine-tune the models and to obtain a preliminary measurement of the performance. The models were then validated on the test set, using the concordance index as the metric. In addition, alternative versions of the models were developed using tumor recurrence as an adjunct feature to evaluate its impact on predictive performance. Finally, the selected CT and PET features were combined to build a further Cox model. Results: The genetic algorithm was superior to the LASSO regression for feature selection. The best performing model was the Cox model, which was built using the selected CT features; it achieved a concordance index score of 0.707. With the addition of tumor recurrence as a predictive feature, the Cox CT model reached a concordance index score of 0.776. PET features, however, proved to be inadequate for survival prediction. The CT model performed better than the model with combined PET and CT features. Conclusions: The results showed that radiomic features can be used to successfully predict survival probability in cervical cancer patients. In particular, CT radiomic features proved to be better predictors than PET radiomic features in this specific case.
引用
收藏
页数:10
相关论文
共 23 条
[1]   Radiomics in cervical cancer: Current applications and future potential [J].
Ai, Yao ;
Zhu, Haiyan ;
Xie, Congying ;
Jin, Xiance .
CRITICAL REVIEWS IN ONCOLOGY HEMATOLOGY, 2020, 152
[2]  
Akaike H., 1973, 2 INT S INF THEOR, P267
[3]  
COX DR, 1972, J R STAT SOC B, V34, P187
[4]   EVALUATING THE YIELD OF MEDICAL TESTS [J].
HARRELL, FE ;
CALIFF, RM ;
PRYOR, DB ;
LEE, KL ;
ROSATI, RA .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 1982, 247 (18) :2543-2546
[5]   18F-FDG PET Uptake Characterization Through Texture Analysis: Investigating the Complementary Nature of Heterogeneity and Functional Tumor Volume in a Multi-Cancer Site Patient Cohort [J].
Hatt, Mathieu ;
Majdoub, Mohamed ;
Vallieres, Martin ;
Tixier, Florent ;
Le Rest, Catherine Cheze ;
Groheux, David ;
Hindie, Elif ;
Martineau, Antoine ;
Pradier, Olivier ;
Hustinx, Roland ;
Perdrisot, Remy ;
Guillevin, Remy ;
El Naqa, Issam ;
Visvikis, Dimitris .
JOURNAL OF NUCLEAR MEDICINE, 2015, 56 (01) :38-44
[6]   RANDOM SURVIVAL FORESTS [J].
Ishwaran, Hemant ;
Kogalur, Udaya B. ;
Blackstone, Eugene H. ;
Lauer, Michael S. .
ANNALS OF APPLIED STATISTICS, 2008, 2 (03) :841-860
[7]   Radiomic signature as a predictive factor for lymph node metastasis in early-stage cervical cancer [J].
Kan, Yangyang ;
Dong, Di ;
Zhang, Yuchen ;
Jiang, Wenyan ;
Zhao, Nannan ;
Han, Lu ;
Fang, Mengjie ;
Zang, Yali ;
Hu, Chaoen ;
Tian, Jie ;
Li, Chunming ;
Luo, Yahong .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2019, 49 (01) :304-310
[8]  
Kikinis R, 2014, Intraoperative imaging image-guided ther, P277, DOI DOI 10.1007/978-1-4614-7657-3_19
[9]   Radiomics: the process and the challenges [J].
Kumar, Virendra ;
Gu, Yuhua ;
Basu, Satrajit ;
Berglund, Anders ;
Eschrich, Steven A. ;
Schabath, Matthew B. ;
Forster, Kenneth ;
Aerts, Hugo J. W. L. ;
Dekker, Andre ;
Fenstermacher, David ;
Goldgof, Dmitry B. ;
Hall, Lawrence O. ;
Lambin, Philippe ;
Balagurunathan, Yoganand ;
Gatenby, Robert A. ;
Gillies, Robert J. .
MAGNETIC RESONANCE IMAGING, 2012, 30 (09) :1234-1248
[10]   Radiomics: the bridge between medical imaging and personalized medicine [J].
Lambin, Philippe ;
Leijenaar, Ralph T. H. ;
Deist, Timo M. ;
Peerlings, Jurgen ;
de Jong, Evelyn E. C. ;
van Timmeren, Janita ;
Sanduleanu, Sebastian ;
Larue, Ruben T. H. M. ;
Even, Aniek J. G. ;
Jochems, Arthur ;
van Wijk, Yvonka ;
Woodruff, Henry ;
van Soest, Johan ;
Lustberg, Tim ;
Roelofs, Erik ;
van Elmpt, Wouter ;
Dekker, Andre ;
Mottaghy, Felix M. ;
Wildberger, Joachim E. ;
Walsh, Sean .
NATURE REVIEWS CLINICAL ONCOLOGY, 2017, 14 (12) :749-762